[llvm] [AMDGPU][FixIrreducible][UnifyLoopExits] Support callbr with inline-asm (PR #149308)

[Robert Imschweiler via llvm-commits]

================
@@ -342,3 +345,55 @@ std::pair<BasicBlock *, bool> ControlFlowHub::finalize(
 
   return {FirstGuardBlock, true};
 }
+
+BasicBlock *ControlFlowHub::createCallBrTarget(
+    CallBrInst *CallBr, BasicBlock *Succ, unsigned SuccIdx, bool AttachToCallBr,
+    CycleInfo *CI, DomTreeUpdater *DTU, LoopInfo *LI) {
+  BasicBlock *CallBrBlock = CallBr->getParent();
+  BasicBlock *CallBrTarget =
+      BasicBlock::Create(CallBrBlock->getContext(),
+                         CallBrBlock->getName() + ".target." + Succ->getName(),
+                         CallBrBlock->getParent());
+  // Rewire control flow from callbr to the new target block.
+  Succ->replacePhiUsesWith(CallBrBlock, CallBrTarget);
+  CallBr->setSuccessor(SuccIdx, CallBrTarget);
+  // Jump from the new target block to the original successor.
+  BranchInst::Create(Succ, CallBrTarget);
+  if (LI) {
+    if (Loop *L = LI->getLoopFor(AttachToCallBr ? CallBrBlock : Succ)) {
+      bool AddToLoop = true;
+      if (AttachToCallBr) {
+        // Check if the loops are disjoint. In that case, we do not add the
+        // intermediate target to any loop.
+        if (auto *LL = LI->getLoopFor(Succ);
+            LL && !L->contains(LL) && !LL->contains(L))
+          AddToLoop = false;
+      }
+      if (AddToLoop)
+        L->addBasicBlockToLoop(CallBrTarget, *LI);
+    }
+  }
+  if (CI) {
+    if (auto *C = CI->getCycle(AttachToCallBr ? CallBrBlock : Succ); C) {
+      bool AddToCycle = true;
+      if (AttachToCallBr) {
+        // Check if the cycles are disjoint. In that case, we do not add the
+        // intermediate target to any cycle.
+        if (auto *CC = CI->getCycle(Succ); CC) {
+          auto *CommonC = CI->getSmallestCommonCycle(C, CC);
----------------
ro-i wrote:

done

https://github.com/llvm/llvm-project/pull/149308